from io import open
import glob
def findFiles(path):
return glob.glob(path)
#print(findFiles('nlpdata/data/names/*.txt'))
import unicodedata
import string
# 所有的英文字母
all_letters = string.ascii_letters + " .,;'"
n_letters = len(all_letters)
# Turn a Unicode string to plain ASCII, thanks to http://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
and c in all_letters
)
#print(unicodeToAscii('Ślusàrski'))
# Build the category_lines dictionary, a list of names per language
category_lines = {}
all_categories = []
# Read a file and split into lines
def readLines(filename):
lines = open(filename, encoding='utf-8').read().strip().split('\n')
return [unicodeToAscii(line) for line in lines]
for filename in findFiles('F:/实验9-16/实验8 基于RNN判别姓名的国别/data/names/*.txt'):
category = filename.split('/')[-1].split('.')[0]
category = category.split('\\')[1]
all_categories.append(category)
lines = readLines(filename)
category_lines[category] = lines
n_categories = len(all_categories)
import torch
# Find letter index from all_letters, e.g. "a" = 0
# 字母所在位置
def letterToIndex(letter):
return all_letters.find(letter)
# Just for demonstration, turn a letter into a <1 x n_letters> Tensor
def letterToTensor(letter):
tensor = torch.zeros(1, n_letters)
# One-hot encoding
tensor[0][letterToIndex(letter)] = 1
return tensor
# Turn a line into a <line_length x 1 x n_letters>,
# or an array of one-hot letter vectors
def lineToTensor(line):
tensor = torch.zeros(len(line), 1, n_letters)
#print(tensor)
for li, letter in enumerate(line):
tensor[li][0][letterToIndex(letter)] = 1
return tensor
import torch.nn as nn
from torch.autograd import Variable
# Creating the network
class RNN(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(RNN, self).__init__()
self.hidden_size = hidden_size
self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
self.i2o = nn.Linear(input_size + hidden_size, output_size)
self.softmax = nn.LogSoftmax(dim=1)
def forward(self, input, hidden):
combined = torch.cat((input, hidden), 1)
hidden = self.i2h(combined)
output = self.i2o(combined)
output = self.softmax(output)
return output, hidden
# 初始化第一个隐藏层输入
def initHidden(self):
return Variable(torch.zeros(1, self.hidden_size))
# our model
n_hidden = 128
rnn = RNN(n_letters, n_hidden, n_categories)
# 类别
def categoryFromOutput(output):
top_n, top_i = output.data.topk(1) # Tensor out of Variable with .data
category_i = top_i[0][0]
return all_categories[category_i], category_i
# loss function
criterion = nn.NLLLoss()
# Train loop
learning_rate = 0.005 # If you set this too high, it might explode. If too low, it might not learn
def train(category_tensor, line_tensor):
hidden = rnn.initHidden()
rnn.zero_grad()
for i in range(line_tensor.size()[0]):
output, hidden = rnn(line_tensor[i], hidden)
loss = criterion(output, category_tensor)
loss.backward()
# Add parameters' gradients to their values, multiplied by learning rate
for p in rnn.parameters():
p.data.add_(-learning_rate, p.grad.data)
return output, loss.data
# 随机采样训练样本对
import random
def randomChoice(l):
return l[random.randint(0, len(l) - 1)]
def randomTrainingExample():
category = randomChoice(all_categories)
line = randomChoice(category_lines[category])
category_tensor = Variable(torch.LongTensor([all_categories.index(category)]))
line_tensor = Variable(lineToTensor(line))
return category, line, category_tensor, line_tensor
import time
import math
n_iters = 200000
print_every = 10000
plot_every = 1000
# Keep track of losses for plotting
current_loss = 0
all_losses = []
def timeSince(since):
now = time.time()
s = now - since
m = math.floor(s / 60)
s -= m * 60
return '%dm %ds' % (m, s)
start = time.time()
for iter in range(1, n_iters + 1):
category, line, category_tensor, line_tensor = randomTrainingExample()
output, loss = train(category_tensor, line_tensor)
current_loss += loss
# Print iter number, loss, name and guess
if iter % print_every == 0:
guess, guess_i = categoryFromOutput(output)
correct = '✓' if guess == category else '✗ (%s)' % category
print('%d %d%% (%s) %.4f %s / %s %s' % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))
# Add current loss avg to list of losses
if iter % plot_every == 0:
all_losses.append(current_loss / plot_every)
current_loss = 0
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
plt.figure()
plt.plot(all_losses)
plt.show()
# 矩阵
confusion = torch.zeros(n_categories, n_categories)
n_confusion = 10000
# Just return an output given a line
def evaluate(line_tensor):
hidden = rnn.initHidden()
for i in range(line_tensor.size()[0]):
output, hidden = rnn(line_tensor[i], hidden)
return output
# Go through a bunch of examples and record which are correctly guessed
for i in range(n_confusion):
category, line, category_tensor, line_tensor = randomTrainingExample()
output = evaluate(line_tensor)
guess, guess_i = categoryFromOutput(output)
category_i = all_categories.index(category)
confusion[category_i][guess_i] += 1
# Normalize by dividing every row by its sum
for i in range(n_categories):
confusion[i] = confusion[i] / confusion[i].sum()
# Set up plot
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(confusion.numpy())
fig.colorbar(cax)
# Set up axes
ax.set_xticklabels([''] + all_categories, rotation=90)
ax.set_yticklabels([''] + all_categories)
# Force label at every tick
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
# sphinx_gallery_thumbnail_number = 2
plt.show()给出修正后的完整程序Ok？
在ndnSIM运行过程中遇到日志中缺失Forwarder转发信息的问题，使用NS_LOG=nfd.Forwarder无效。原因是不同ndnSIM版本对应的日志模块不同。在ndnSIM 2.7版本中，正确模块为ndn-cxx.nfd.Forwarder。通过查看所有有效参数列表来确认正确的日志模块设置。
扫一扫
1902
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
